Ashwini Kukade
Ashwini Kukade has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
Abhishek Dhore
MIT School of Computing, MIT ADT University, Pune, India
1 shared publication- Dhananjay Bhagat
Vishwakarma Institute of Technology, Pune, India
1 shared publication - Hitesh Gehani
Ramdeobaba University
1 shared publication Kamlesh Kalbande
G.H. Raisoni College of Engineering, Nagpur, India
1 shared publication- Manjushree Nayak
Amity University, Raipur, India
1 shared publication - Parul Dubey
Symbiosis Institute of Technology, Nagpur Campus, Symbiosis International (Deemed University), Pune, India
1 shared publication
Latest Publications
- Open Access
- 2 May 2025
- Published by Institute of Advanced Engineering and Science in Bulletin of Electrical Engineering and Informatics
- Vol. 14 (3) , 2370-2379
Enhancing realism in handwritten text images with generative adversarial networks
Image synthesis is particularly important for applications that want to create realistic handwritten documents, which is why handwritten text generation is a critical area within its domain. Even with today's highly advanced technology, generating diverse and accurate representations of human handwriting is still a tough problem because of the variability in style. In this study, we tackle the problem of instability during the training phase of generative adversarial networks (GANs) for generating handwritten text images. Using the MNIST dataset, which includes 60,000 training and 10,000 test images of handwritten digits, we trained a GAN model to generate synthetic handwritten images. The methodology involves optimizing both the generator and discriminator using adversarial training, binary cross-entropy loss, as well as the optimizer Adam. A brand-new decaying learning rate schedule was introduced to speed up convergence. Performance was evaluated using the Fréchet inception distance (FID) metric. The results show that this model effectively generated high-quality synthetic images of handwritten digits, which resembled real data closely in the face of it all and also that there was a steady reduction in FID scores across epochs indicating improved performance.
- 2 May 2025
- Published by Institute of Advanced Engineering and Science in Bulletin of Electrical Engineering and Informatics
- Vol. 14 (3) , 2370-2379
Open AccessEnhancing realism in handwritten text images with generative adversarial networks
Image synthesis is particularly important for applications that want to create realistic handwritten documents, which is why handwritten text generation is a critical area within its domain. Even with today's highly advanced technology, generating diverse and accurate representations of human handwriting is still a tough problem because of the variability in style. In this study, we tackle the problem of instability during the training phase of generative adversarial networks (GANs) for generating handwritten text images. Using the MNIST dataset, which includes 60,000 training and 10,000 test images of handwritten digits, we trained a GAN model to generate synthetic handwritten images. The methodology involves optimizing both the generator and discriminator using adversarial training, binary cross-entropy loss, as well as the optimizer Adam. A brand-new decaying learning rate schedule was introduced to speed up convergence. Performance was evaluated using the Fréchet inception distance (FID) metric. The results show that this model effectively generated high-quality synthetic images of handwritten digits, which resembled real data closely in the face of it all and also that there was a steady reduction in FID scores across epochs indicating improved performance.
- 4 January 2024
- Published by IGI Global Scientific Publishing
- p. 159-182
Big Data Preprocessing, Techniques, Integration, Transformation, Normalisation, Cleaning, Discretization, and Binning
“Unleashing the Power of Big Data: Innovative Approaches to Preprocessing for Enhanced Analytics” is a groundbreaking chapter that explores the pivotal role of preprocessing in big data analytics. It introduces diverse techniques to transform raw, unstructured data into a clean, analyzable format, addressing the challenges posed by data volume, velocity, and variety. The chapter emphasizes the significance of preprocessing for accurate outcomes, covers advanced data cleaning, integration, and transformation techniques, and discusses real-time data preprocessing, emerging technologies, and future directions. This chapter is a comprehensive resource for researchers and practitioners, enabling them to enhance data analytics and derive valuable insights from big data.
- 4 January 2024
- Published by IGI Global Scientific Publishing
- p. 159-182
Big Data Preprocessing, Techniques, Integration, Transformation, Normalisation, Cleaning, Discretization, and Binning
“Unleashing the Power of Big Data: Innovative Approaches to Preprocessing for Enhanced Analytics” is a groundbreaking chapter that explores the pivotal role of preprocessing in big data analytics. It introduces diverse techniques to transform raw, unstructured data into a clean, analyzable format, addressing the challenges posed by data volume, velocity, and variety. The chapter emphasizes the significance of preprocessing for accurate outcomes, covers advanced data cleaning, integration, and transformation techniques, and discusses real-time data preprocessing, emerging technologies, and future directions. This chapter is a comprehensive resource for researchers and practitioners, enabling them to enhance data analytics and derive valuable insights from big data.